Image-Text-to-Video
Diffusers
Safetensors
MiniMaxH3ModularPipeline
text-to-video
image-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
MiniMax H3 Prompt Enhancer, powered by a fine-tuned 350M-parameter model
#58
by geocine - opened
The model is only around 700 MB. You can try it here:
https://huggingface.co/spaces/geocine/MiniMax-H3-Prompt-Enhancer
I’m also working on a complete reference pipeline with WebGPU integration. The goal is to run prompt enhancement privately on WebGPU or CPU, without relying on ZeroGPU or competing with the GPU resources used for local or server-side video generation.